基于WiFi的一种改进的室内定位算法

摘要

为解决室内定位中算法定位精度不高、误差偏大的问题,在原有指纹匹配算法的基础上,提出了一种新的信号能量加权改进接收信号强度的方法.通过对改进后的信号能量进行均值滤波和阈值滤波处理,改善离线建立指纹库阶段建库数据源.在线匹配阶段,改进WKNN算法,利用方差加权结合欧式距离倒数进行相似度匹配.该方法与目前的WKNN算法相比,在减少复杂度的同时,对定位效果进行改善.在不考虑AP组合对定位结果影响的情况下,仿真结果表明所提出的改进算法能明显提高定位精度.%In order to solve the problems that the positioning accuracy of indoor positioning algorithm is not high and the error is too large,a new method of signal energy weighting to improve the strength of received signal is proposed based on the original fingerprint matching algorithm.Through the mean signal filtering and threshold filtering of the improved signal energy,the data source of the fingerprint database is improved.In the online matching stage,the WKNN algorithm is improved,and the variance weighting is used to match the reciprocal of the European distance to match the similarity.Compared with the current WKNN algorithm,this method improves the localization effect while reducing the complexity.Without considering the influence of AP combination on the positioning results,the simulation results show that the improved algorithm can improve the positioning accuracy obviously.